The appeal of data

I’m working on my next blog on non-parametric learning. I hope to publish early next week. In the meantime, take a look at the three graphs depicting the same stress/extension data for a rubber below and tell me which you prefer via this link. There is no correct answer, each represents a different view of learning. I’ll describe how I generated each curve in my next blog. Don’t worry if you are not familiar with stress/extension data, you are not alone! The point of graphics is to convey information to widest possible audience in the most straightforward way possible, so your opinion is still valuable to me. These different ways of graphically describing the same data challenge us to think about what is it we are hoping to know that we didn’t know before, and, then, to ask what can we do differently now that we know it?

Feel free to add comments to the blog, if you’d like to let me know why you’ve made your particular choice.

Graph number 1:



Graph number 2:



Graph number 3:



6 thoughts on “The appeal of data

  1. Hi Nigel,

    Number Three looks like a line generated from the Mooney-Rivlin equation or similar. It fits the elastic region at low strain, but does not consider the relaxation at higher strains (from disentanglements) nor the strain hardening at the very high strain.

    Number One looks like the data points are connected by straight lines – such as seen in undergrad lab reports when they do not try to compare their results to theory.

    Number Two has captured the S-shaped trend in the data very nicely. It is also the most attractive aesthetically. I definitely prefer Number Two.



    1. Hi Joe,

      absolutely right. After writing that there was no correct answer I realised that number one, which no-one chose thankfully, is the one I encourage my students to avoid!


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s